Quick/Comparisons
32 | Gaming | 6 |
47 | Workstation | 9 |
32 | AI/ML |
Compare with something else?
Compare Nvidia RTX 3000 with another →9 |
56 | Energy Efficiency | 86 |
40 | Quick Comparison Final Score | 20 |
| AD106 | Graphics Processor | Krackan Point |
| 4608 | Cores | 256 |
| 144 / 48 | TMUs / ROPs | 16 / 8 |
| 2931.27 | Blender GPU | 122.02 |
| 70 | Forza Horizon 5 | 13 |
| 98 | The Witcher 3 | 12 |
| 132 | Counter-Strike 2 | 18 |
| 83 | Far Cry 6 | 16 |
| 54 | Hogwarts Legacy | - |
| 73 | Call of Duty | 19 |
| 51 | Ghost of Tsushima | 9 |
| 64 | Cyberpunk 2077 | 9 |
| 102 | Tomb Raider | 17 |
| 81 | Average FPS | 13 |
| 100 | 1080p High | 18 |
| 81 | 1080p Ultra | 13 |
| 59 | 1440p Ultra | 10 |
| 32 | 4K Ultra | - |
| High | Margin of Error | High |
| 119612 | GB6 Compute Score | 14025 |
| 196.1 img/sec | Background Blur | 31.8 img/sec |
| 118.9 img/sec | Face Detection | 16.8 img/sec |
| 4.22 Gpixels/sec | Horizon Detection | 0.46 Gpixels/sec |
| 5.54 Gpixels/sec | Edge Detection | 0.58 Gpixels/sec |
| 6.07 Gpixels/sec | Gaussian Blur | 0.42 Gpixels/sec |
| 1.4 Gpixels/sec | Feature Matching | 0.18 Gpixels/sec |
| 573 Gpixels/sec | Stereo Matching | 52.5 Gpixels/sec |
| 17661.3 FPS | Particle Physics | 2048.6 FPS |
| OpenCL | API | OpenCL |
| 16040 | G3D Mark Score | — |
| 543 | G2D Mark | — |
| 140 FPS | DirectX 11 | — |
| 80 FPS | DirectX 12 | — |
| 5988 Ops/s | GPU Compute | — |
| 17574 | GB6 ML Single Precision | 4884 |
| 28903 | GB6 ML Half Precision | 6067 |
| 13159 | GB6 ML Quantized | 3946 |
| 7093 | Image Classification (SP) | 1988 |
| 14759 | Image Segmentation (HP) | 2184 |
| 23321 | Image Super Resolution (Q) | 4788 |
| 29211 | Face Detection (HP) | 6857 |
| 87917 | Pose Estimation (Q) | 17396 |
| 3395 | Text Classification (SP) | 1628 |
| 3464 | Machine Translation (HP) | 2053 |
| 8181 | Object Detection (SP) | 1825 |
| 30150 | Depth Estimation (Q) | 8471 |
| 167055 | Style Transfer (SP) | 31032 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 56-104 GPixel/s | Pixel Fill Rate | 23 GPixel/s |
| 168-311 GTexel/s | Texture Fill Rate | 46 GTexel/s |
| 10.7-19.9 TFLOPS | FLOPS (FP32) | 1.5 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 2000 MHz | Memory Clock | — |
| 16000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| Yes | ECC | — |
| 256 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 35-140 W (configurable) | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 188 mm² | Die Size | — |
| 22.9 billion | Transistor Count | — |
| 121.81 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| March 21, 2023 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Ada Lovelace | Architecture | RDNA 3.5 |
| AD106 | GPU Codename | Krackan Point |
| -Intel Core Ultra 7 165Hor above | Recommended CPU | -AMD Ryzen AI 5 340or above |
| 8756 | Time Spy | 1700 |
| 36647 | Solar Bay | 7155 |
| 5210 | Port Royal | 577 |
| 20658 | Fire Strike | 5317 |
| 14961 | Wild Life Extreme | — |
| 51077 | Night Raid | 22727 |
| 9033 | Steel Nomad Lite Score | 1293 |
| — | Base Clock | 400 MHz |
| 1165-2160 MHz (configurable) | Boost Clock | 2900 MHz |
| 4608 | Shading Units | 256 |
| 144 | Texture Mapping Units (TMUs) | 16 |
| 48 | Render Output Units (ROPs) | 8 |
| 36 | Compute Units (Pipelines) | 4 |
| 144 | Tensor Cores | No |
| 36 | Ray-tracing Cores | 4 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 32MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |